INDEX

Explanations

lung

np_max-act · gemini-2.0-flash

references to the lungs and pulmonary system in medical or anatomical contexts.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¾Ģ

-0.35

èĪħ

-0.27

Ã»

-0.26

åĳ¨æľ«

-0.25

ords

-0.25

æ¹

-0.25

lice

-0.25

ĸ

-0.25

Boo

-0.25

orts

-0.24

POSITIVE LOGITS

moth

0.26

è¿ĻæĶ¯

0.24

 policy

0.24

/MPL

0.24

cele

0.24

positor

0.23

upt

0.23

å¤©æ²³

0.23

supply

0.23

uala

0.23

Activations Density 0.011%

lung

references to the lungs and pulmonary system in medical or anatomical contexts.

No Comments

No Known Activations