INDEX

Explanations

ivities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orce

-0.29

 strokes

-0.28

itud

-0.28

leigh

-0.26

ningen

-0.26

Force

-0.26

 Force

-0.25

åĬĽ

-0.25

 Scotch

-0.24

ori

-0.24

POSITIVE LOGITS

å¹´ä»£

0.27

Such

0.27

idl

0.26

æ½¤

0.25

Perm

0.24

ç´§å¼ł

0.24

REAT

0.24

 refer

0.24

åĪĽæĸ°

0.24

èİ²èĬ±

0.23

Activations Density 0.055%

ivities

No Comments

No Known Activations