INDEX

Explanations

away

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[source

-0.29

zzle

-0.25

çģ¶

-0.25

ä¸¸

-0.24

iever

-0.24

gent

-0.24

ATEST

-0.24

 shim

-0.23

erate

-0.23

gie

-0.23

POSITIVE LOGITS

ccb

0.29

æĮĳ

0.26

 Seymour

0.26

 ÑĢÐ¾Ð¶Ð´ÐµÐ½Ð¸Ñı

0.26

boot

0.26

>(()

0.25

Ãºa

0.25

rad

0.24

lee

0.24

<_

0.24

Activations Density 0.002%

away

No Comments

No Known Activations