INDEX

Explanations

Viruses and treatments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dáº«n

-0.29

uchi

-0.28

REE

-0.27

è©±

-0.25

vet

-0.24

è¶ĭåĬ¿

-0.24

 tast

-0.24

çĪ¨

-0.24

ãĤīãģļ

-0.24

idget

-0.23

POSITIVE LOGITS

åĬŀäºĭ

0.29

ãģĤãģŁãĤĬ

0.27

å±±è°·

0.24

ä»Ģä¹Īåľ°æĸ¹

0.24

 graduation

0.24

 trunc

0.24

ä»Ģä¹Īä¸ľè¥¿

0.23

['_

0.23

presence

0.23

 integration

0.23

Activations Density 24.099%

Viruses and treatments

No Comments

No Known Activations