INDEX

Explanations

on

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Business

-0.28

objectId

-0.27

 business

-0.26

business

-0.25

èĭĵ

-0.25

åį¯

-0.24

ours

-0.24

ÑģÐ¾Ð½

-0.24

igsaw

-0.23

å¦Ĥæŀľä¸įæĺ¯

-0.23

POSITIVE LOGITS

ft

0.28

 volta

0.27

å¸ķ

0.27

twe

0.26

pat

0.26

rie

0.25

 tomb

0.25

 cunt

0.24

empor

0.24

äº²

0.24

Activations Density 0.004%

on

No Comments

No Known Activations