INDEX

Explanations

its

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

epad

-0.30

å·²æľī

-0.29

enger

-0.28

ptype

-0.26

 earnest

-0.26

Ash

-0.25

æ¦ľ

-0.25

GED

-0.25

et

-0.25

ed

-0.24

POSITIVE LOGITS

#__

0.27

/forms

0.25

è°ħè§£

0.25

 cáº£nh

0.24

ovation

0.24

å¿¤

0.24

otron

0.24

ixin

0.24

æ¦ĤåĨµ

0.24

æĪĸèĢħæĺ¯

0.24

Activations Density 0.004%

its

No Comments

No Known Activations