INDEX

Explanations

Tendon injuries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èľĺèĽĽ

-0.28

Â¥

-0.28

vestment

-0.27

 Twins

-0.25

å·³

-0.25

ç»ĪæŃ¢

-0.25

Arb

-0.24

eating

-0.24

<:

-0.24

eu

-0.23

POSITIVE LOGITS

åİĨåı²æĸ°

0.30

çļĦè¯Ŀé¢ĺ

0.29

è¯Ŀé¢ĺ

0.27

ä¸įè´Ł

0.26

OWN

0.26

 topic

0.26

atis

0.25

æ¯¡

0.25

Pt

0.24

AppState

0.24

Activations Density 0.001%

Tendon injuries

No Comments

No Known Activations