INDEX

Explanations

targeting

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

ç»ĵ

-0.32

å©ļå§»

-0.31

 recourse

-0.28

ellung

-0.28

Ð·Ð°

-0.28

\Request

-0.27

azole

-0.26

é¡¶

-0.25

 Dmit

-0.25

çĶŁäº§èĥ½åĬĽ

-0.25

POSITIVE LOGITS

inati

0.28

èĻŁ

0.27

upal

0.26

 leader

0.26

leader

0.25

 Leader

0.24

 TARGET

0.24

pic

0.24

 caut

0.24

 PARTICULAR

0.24

Activations Density 0.017%

targeting

No Comments

No Known Activations