INDEX

Explanations

Attempt or near-occurrence

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦º

-0.27

quality

-0.27

è´¨

-0.26

æ´¾

-0.25

 Present

-0.25

rag

-0.25

 Attr

-0.25

åĭĺ

-0.25

éĴĿ

-0.24

onders

-0.24

POSITIVE LOGITS

.Failure

0.26

upiter

0.25

å·®çĤ¹

0.24

inx

0.24

_WIFI

0.24

ç¯¡

0.24

_dummy

0.23

çĥ

0.23

æĪĲåĬŁ

0.23

çĻ½çĻ½

0.23

Activations Density 0.004%

Attempt or near-occurrence

No Comments

No Known Activations