INDEX

Explanations

first

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

_Free

-0.26

æ·¹

-0.25

opus

-0.25

imar

-0.24

ourmet

-0.24

ported

-0.24

(OP

-0.24

<Component

-0.24

 duplication

-0.23

urrect

-0.23

POSITIVE LOGITS

 consultations

0.30

stile

0.28

åĭĺå¯Ł

0.27

èµĽ

0.27

oppable

0.27

 consultation

0.26

äº¤æµģ

0.26

 visit

0.26

è¯Ĭ

0.26

 diag

0.26

Activations Density 0.060%

first

No Comments

No Known Activations