INDEX

Explanations

8

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

ordes

-0.30

å±¥

-0.28

æ»¡

-0.28

èĲ½

-0.27

vot

-0.26

">&#

-0.26

plug

-0.26

æ»¿

-0.25

 Plaza

-0.25

 drafts

-0.25

POSITIVE LOGITS

 pigeon

0.27

wit

0.25

 boundary

0.25

 astr

0.25

NTN

0.25

 Sabbath

0.25

aida

0.24

 before

0.24

 âĸĪâĸĪ

0.24

 intrusion

0.24

Activations Density 0.001%

8

No Comments

No Known Activations