INDEX

Explanations

Rivers and locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odem

-0.26

kas

-0.26

Accepted

-0.25

acr

-0.24

Verified

-0.24

 Dice

-0.24

Dice

-0.24

ä¸įè§£

-0.24

Dt

-0.24

 prox

-0.24

POSITIVE LOGITS

Est

0.41

est

0.35

ä¼°

0.32

each

0.31

-Col

0.31

ä¼°è®¡

0.31

 each

0.29

-S

0.29

 estimation

0.29

çĽ¸åıį

0.29

Activations Density 0.012%

Rivers and locations

No Comments

No Known Activations