INDEX

Explanations

information security

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kaar

-0.33

iosk

-0.26

asar

-0.26

äºı

-0.26

irk

-0.25

 incontro

-0.25

ius

-0.25

åĽ½æĥħ

-0.25

ickers

-0.24

è§Ħ

-0.24

POSITIVE LOGITS

æ³ł

0.31

áº¥p

0.27

olta

0.27

ArrayType

0.27

å£®å¤§

0.27

otto

0.26

åŀ«

0.25

::_

0.25

ç¬Ļ

0.25

å¯¤

0.24

Activations Density 0.015%

information security

No Comments

No Known Activations