INDEX

Explanations

to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 jokes

-0.27

/tiny

-0.26

 Generation

-0.26

å¤ªå¿«

-0.25

 sausage

-0.25

TÄ°

-0.24

-eslint

-0.24

Generation

-0.24

ainted

-0.24

_generation

-0.24

POSITIVE LOGITS

æĹģ

0.27

adro

0.26

ping

0.26

lections

0.26

eld

0.26

ÃŃc

0.26

 dance

0.25

 dancing

0.25

isor

0.25

tracts

0.25

Activations Density 0.001%

to

No Comments

No Known Activations