INDEX

Explanations

clinical

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

ä½ľèĢħæīĢæľī

-0.27

 Pole

-0.27

rush

-0.26

 Assigned

-0.26

ä¼ģ

-0.25

é©³

-0.25

ç®©

-0.25

á¹ĩ

-0.24

FromFile

-0.24

emap

-0.24

POSITIVE LOGITS

å¼Ħ

0.28

èĦ±ç¦»

0.26

æ³³

0.25

agnostic

0.25

.echo

0.25

è¿½

0.24

agnost

0.24

åĶ¯ä¸Ģ

0.24

elling

0.24

 ethic

0.24

Activations Density 0.029%

clinical

No Comments

No Known Activations