INDEX

Explanations

documents/online content

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

 Planner

-0.28

ools

-0.27

fbe

-0.27

@Inject

-0.25

\Backend

-0.25

scheme

-0.25

éĽķ

-0.25

odon

-0.24

iero

-0.24

ç»ĥ

-0.24

POSITIVE LOGITS

åħ¨æĸĩ

0.26

"[

0.26

contenido

0.25

èµĦè®¯

0.25

ç¨į

0.25

KO

0.25

ONG

0.25

ä¹ĭä¹¡

0.24

èĦ±

0.24

 initialState

0.24

Activations Density 0.041%

documents/online content

No Comments

No Known Activations