INDEX

Explanations

permission

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atory

-0.31

iative

-0.29

wij

-0.27

pheric

-0.26

æ¯įæł¡

-0.25

åĺŀ

-0.25

è¿Ļä¸¤å¤©

-0.25

 organised

-0.25

tone

-0.25

æ·»

-0.24

POSITIVE LOGITS

åħįè´¹

0.28

âīĮ

0.27

arius

0.27

/unit

0.27

orne

0.27

æĬ¢åħĪ

0.27

_fixture

0.25

å®īåħ¨

0.25

 bÄĥng

0.25

 auth

0.24

Activations Density 0.897%

permission

No Comments

No Known Activations