INDEX

Explanations

literature

np_max-act · gemini-2.0-flash

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

 Gast

-0.28

æ±

-0.27

 Reject

-0.26

æĶ»åĬ¿

-0.25

-company

-0.25

å®¹åĻ¨

-0.25

AAC

-0.25

 distancing

-0.25

 desn

-0.24

 Glam

-0.24

POSITIVE LOGITS

iod

0.29

akan

0.29

è¡Įäºº

0.27

imore

0.26

è¯·çĤ¹åĩ»

0.25

_squared

0.24

ledon

0.24

 shut

0.24

ÊĤ

0.24

ctic

0.23

Activations Density 0.002%

literature

No Comments

No Known Activations