INDEX

Explanations

anger

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

çĥŃå¿ĥ

-0.29

egis

-0.29

[at

-0.26

elor

-0.26

 significance

-0.26

æĪĲåĳĺåįķä½į

-0.25

 eventual

-0.25

æĺ¯æĪĳä»¬

-0.25

elmet

-0.24

 panties

-0.24

POSITIVE LOGITS

ault

0.29

æ¯Ľæ³½

0.27

ftar

0.25

esto

0.25

 ground

0.25

æĵĤ

0.24

gob

0.24

Launch

0.24

throp

0.24

wen

0.23

Activations Density 21.547%

anger

No Comments

No Known Activations