INDEX

Explanations

injections

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

.OP

-0.28

 infl

-0.28

 freund

-0.27

 Olympic

-0.26

ursive

-0.26

urs

-0.25

estic

-0.25

å¹³åĿĩ

-0.25

rio

-0.24

doi

-0.24

POSITIVE LOGITS

_GAP

0.28

fad

0.26

<button

0.26

åĬłçıŃ

0.25

ìŀ¬

0.25

aty

0.25

indh

0.25

æģĴå¤§

0.25

áº¥p

0.25

ÐµÐ½Ð°

0.25

Activations Density 0.034%

injections

No Comments

No Known Activations