INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oud

-0.27

net

-0.24

æľīå¤ļå¤§

-0.23

_permission

-0.23

 seams

-0.23

é½ĳ

-0.23

åĹŀ

-0.23

é²»

-0.23

å¤´çĸ¼

-0.22

ä¸ºæĤ¨æıĲä¾Ľ

-0.22

POSITIVE LOGITS

èĤ¥

0.27

æĭĽ

0.27

 defensively

0.25

åıĭ

0.25

é«¦

0.25

è¶³

0.24

æĬ½

0.24

posted

0.24

 exotic

0.24

 Monk

0.24

Activations Density 0.028%

punctuation

No Comments

No Known Activations