INDEX

Explanations

ac

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lius

-0.26

 theta

-0.25

OfType

-0.25

PEAT

-0.25

ENTA

-0.24

 Lambda

-0.24

æĹĭè½¬

-0.24

 improper

-0.24

æ¹¾

-0.24

å¯¹æŃ¤

-0.23

POSITIVE LOGITS

ç§»åĪ°

0.29

ëª½

0.27

:selected

0.26

 scopes

0.26

cing

0.26

 collaborations

0.25

 collaboration

0.24

 excav

0.24

cs

0.24

æ£ł

0.24

Activations Density 0.075%

ac

No Comments

No Known Activations