INDEX

Explanations

lactation

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

èĪ

-0.28

_pas

-0.28

pas

-0.26

agli

-0.25

 tone

-0.25

ä½ĵä¼ļåĪ°

-0.25

WindowSize

-0.25

 passive

-0.25

.setHorizontalGroup

-0.24

pas

-0.24

POSITIVE LOGITS

ç¨³å®ļ

0.29

èĥĿ

0.28

æ²»çĸĹæĸ¹æ³ķ

0.27

ä¸įç¨³å®ļ

0.26

zioni

0.26

alie

0.26

enstein

0.26

çŀĴ

0.26

ç¼Ļ

0.26

mania

0.25

Activations Density 0.016%

lactation

No Comments

No Known Activations